Spurious correlation #1,488 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Bachelor's degrees awarded in Parks & Recreation and the second variable is Total U.S. grain export volume. The chart goes from 2012 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Bachelor's degrees awarded in Parks & Recreation and the second variable is Total U.S. grain export volume. The chart goes from 2012 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As more people became educated in these fields, they realized the importance of outdoor activities. This led to a surge in demand for recreational sports such as wheat tossing and corn husking, ultimately boosting the production and export of grains.

^{Show image generation prompt} Model: dalle-3
Prompt: "Generate [ A photo-realistic image ] of a group of proud graduates wearing caps and gowns in a sunlit park, holding their Bachelor's degree certificates in parks, recreation, leisure, fitness, and kinesiology. They are surrounded by towering silos filled with grains, as workers load massive shipments onto cargo ships bound for export. Keep the visual simple and do not include any words or speech bubbles." The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Bachelor's degrees awarded in Parks, recreation, leisure, fitness, and kinesiology and Total U.S. grain export volume. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Oragami An image that looks like it is a scene from a Pixar movie A photo-realistic image Brutalism An image that looks like it is a scene from 'Star Wars'
ChatGPT: A photo-realistic image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Bachelor's degrees awarded in Parks, recreation, leisure, fitness, and kinesiology and Total U.S. grain export volume together. Keep the description simple.
ChatGPT: In a sunlit park, a group of graduates wearing caps and gowns stand proudly, holding their Bachelor's degree certificates in parks, recreation, leisure, fitness, and kinesiology. Surrounding them are towering silos filled with grains, as workers load massive shipments onto cargo ships bound for export.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A photo-realistic image ] and depicting this scene: In a sunlit park, a group of graduates wearing caps and gowns stand proudly, holding their Bachelor's degree certificates in parks, recreation, leisure, fitness, and kinesiology. Surrounding them are towering silos filled with grains, as workers load massive shipments onto cargo ships bound for export. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: "Generate [ A photo-realistic image ] of a group of proud graduates wearing caps and gowns in a sunlit park, holding their Bachelor's degree certificates in parks, recreation, leisure, fitness, and kinesiology. They are surrounded by towering silos filled with grains, as workers load massive shipments onto cargo ships bound for export. Keep the visual simple and do not include any words or speech bubbles."

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Bachelor's degrees awarded in Parks, recreation, leisure, fitness, and kinesiology caused Total U.S. grain export volume to increase.

AI academic paper

(Because p < 0.01)

Peculiar Parks, Plentiful Protein: Examining the Exquisite Entanglement Between Bachelor's Degrees in Parks, Recreation, Leisure, Fitness, and Kinesiology and Total U.S. Grain Export Volume

The Journal of Recreationomics

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Bachelor's degrees awarded in Parks, recreation, leisure, fitness, and kinesiology and Total U.S. grain export volume. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

Here are the title, abstract, literature review, and results sections. Please harken back to 1-2 of the goofy items in the literature review, but pretend to take them completely seriously. Discuss how your results supported the prior research.

Do not write a conclusion. I will add a conclusion after this.

[[TITLE]]
Peculiar Parks, Plentiful Protein: Examining the Exquisite Entanglement Between Bachelor's Degrees in Parks, Recreation, Leisure, Fitness, and Kinesiology and Total U.S. Grain Export Volume

[[ABSTRACT]]
This peculiar paper plunges into the perplexing partnership between the output of Bachelor's degrees in the fields of parks, recreation, leisure, fitness, and kinesiology and the total volume of grain exports in the United States. With an eye toward uncovering unforeseen connections, we leveraged data from the National Center for Education Statistics and Statista to explore this rather enigmatic correlation. Our findings unveiled a robust correlation coefficient of 0.7988008, with a statistically significant p-value of less than 0.01 for the years 2012 to 2021.

Our study delves deep into the realms of academia and agriculture, seeking to shed light on this unexpected affiliation. While the conventional academic pursuits in this domain may not seem intertwined with the world of grain exports at first glance, our analysis suggests a peculiar juxtaposition. So join us on this scholarly sojourn as we untangle the enigma of education and agriculture, and unearth the unexpected intersections that abound in our ever-curious world.

[[LITERATURE REVIEW]]
The link between educational pursuits and the broader economy has long been a subject of scholarly inquiry. Smith et al. (2015) investigated the impact of educational attainment on labor market outcomes, while Doe and Jones (2018) examined the relationship between college majors and post-graduation employment. However, our foray into the intriguing intersection of academic awards in parks, recreation, leisure, fitness, and kinesiology with U.S. grain exports leads us down an unexpected rabbit hole, much like stumbling upon a pair of misplaced hiking boots in a bustling grain silo.
Turning our attention beyond the traditional confines of academic publications, we encounter a treasure trove of literature that sheds light, albeit tangentially, on the curious correlation at hand. The book "Leisure and Recreation Management" by Torkildsen (2017) provides a comprehensive overview of the management and operation of leisure and recreational facilities, offering insights that may appear unrelated to our focus, much like discovering a stray golf ball amidst a bustling farmer's market.
Shifting our gaze to the realm of fiction, we find ourselves presented with intriguing narratives that, while not directly addressing our inquiry, bear titles that could suggest a peripheral connection. "Wheat Fields and Fitness: A Tale of Two Territories" by Novel Author (2020) and "Adventures in Agriculture: A Journey of Physical Prowess" by Imaginary Writer (2016) beckon us with their seemingly relevant titles, like a trail of breadcrumbs luring us deeper into the overgrown maze of scholarly investigation.
In the modern epoch of digital discourse, social media platforms echo with the voices of individuals offering their own musings on the curious relationship between education in park-related disciplines and the agricultural export landscape. A tweet from @LeisureEnthusiast reads, "Who would have thought that a degree in leisure management could hold the secret to the soybean market's whims? #UnexpectedConnections #LeisurelyLearnings," highlighting the unexpected confluence of academia and agriculture, reminiscent of discovering a whimsical farm animal in the middle of a bustling university campus.
As we wade through this diverse ocean of sources, we are reminded that the pursuit of knowledge often leads us down uncharted paths, where unexpected discoveries and serendipitous connections await, much like stumbling upon a clown juggling bowling pins in the somber silence of a library.

[[RESULTS]]
The statistical analysis of the data gathered from the National Center for Education Statistics and Statista yielded some compelling results. Over the period from 2012 to 2021, our research unearthed a robust correlation coefficient of 0.7988008 between the number of Bachelor's degrees awarded in parks, recreation, leisure, fitness, and kinesiology and the total volume of grain exports in the United States. This finding suggests a fairly strong positive linear relationship between the two variables, reminiscent of finding a well-hidden Easter egg in an expansive, data-filled meadow.
Furthermore, the calculated r-squared value of 0.6380828 indicates that approximately 63.8% of the variability in the grain export volume can be explained by the variation in the number of Bachelor's degrees awarded in the specified fields. This result is not dissimilar to finally connecting the dots in a complicated maze, discovering the unexpected way in which these seemingly unrelated realms intertwine.
The p-value of less than 0.01 for the correlation coefficient provides strong evidence against the null hypothesis, firmly establishing the statistical significance of the relationship. A result this striking is akin to stumbling upon a diamond in the rough, or perhaps a kernel of wheat in a haystack.
Moreover, the scatterplot presented in Fig. 1 portrays a clear, upward-sloping trend, illustrating the conspicuous correlation between the variables. This visualization is akin to witnessing a magic trick that reveals the unexpected connection between two distinct realms, leaving scholars and spectators alike in awe of the unexpected dance of academia and agriculture.
In summary, our findings illuminate a previously overlooked harmony between the confounding domains of higher education and grain exports, highlighting the necessity of exploring uncharted intellectual territories and embracing the delightful surprises that await amidst the labyrinth of data and knowledge.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our investigation has uncovered a remarkably robust and statistically significant correlation between the number of Bachelor's degrees awarded in the fields of parks, recreation, leisure, fitness, and kinesiology, and the total volume of grain exports in the United States from 2012 to 2021. This unexpected connection has redefined the perception of these seemingly disparate domains, much like stumbling upon a squirrel doing yoga in a cornfield. Our findings not only underscore the importance of delving into unconventional intersections of academic and economic sectors, but also emphasize the necessity of keeping an open mind in scholarly pursuits, much like a farmer closely monitoring both weather patterns and wheat growth.

Our results stand in alignment with prior research that has delved into the intriguing interplay between educational pursuits and economic phenomena. The stark correlation coefficient we have unearthed echoes the sentiment expressed by Smith et al. (2015), who illuminated the impact of educational attainment on labor market outcomes. In a similar vein, the statistically significant p-value for our correlation coefficient reinforces the findings of Doe and Jones (2018), who examined the relationship between college majors and post-graduation employment. The unexpected juxtaposition of parks and grains, much like discovering a stunning sunset at a fitness center, challenges traditional academic boundaries and underscores the need for interdisciplinary exploration.

As we reflect on the unexpected confluence of parks and grain, one is reminded of the compelling narratives and seemingly tangential literature reviewed in our inquiry. Torkildsen's (2017) comprehensive overview of leisure management and recreational facilities may appear unrelated at first, much like finding a pair of misplaced hiking boots in a bustling grain silo. However, our findings mirror the indirect relevance of such insights, much like stumbling upon a stray golf ball amidst a bustling farmer's market. Likewise, the fictional titles "Wheat Fields and Fitness: A Tale of Two Territories" by Novel Author (2020) and "Adventures in Agriculture: A Journey of Physical Prowess" by Imaginary Writer (2016) remind us that unexpected connections often lurk beneath seemingly unrelated endeavors, much like encountering a whimsical farm animal in the middle of a bustling university campus.

The striking correlation coefficient and r-squared value we have uncovered highlight the consequential nature of the relationship between Bachelor's degrees in these specific fields and U.S. grain exports. Our results, akin to finding a well-hidden Easter egg in an expansive, data-filled meadow, further emphasize the unpredictable nature of academic inquiry and the value of unearthing unexpected connections amidst scholarly exploration. This fortuitous discovery, much like finding a kernel of wheat in a haystack, demands continued investigation, showcasing the delightful surprises that await amidst the labyrinth of data and knowledge, much like stumbling upon a clown juggling bowling pins in the somber silence of a library.

In light of these findings, we urge future researchers to embrace the serendipitous intersections of academia and economy and to engage in further exploration of uncharted intellectual territories, much like finally connecting the dots in a complicated maze. This interdisciplinary journey holds the promise of unveiling novel insights and enriching our understanding of the intricate web of relationships that underpin our interconnected world, much like witnessing a magic trick that reveals the unexpected connection between two distinct realms. Through this scholarly sojourn, we hope to continue unraveling the captivating mysteries that linger at the intriguing juncture of academia and agriculture, much like a trail of breadcrumbs luring us deeper into the overgrown maze of scholarly investigation.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Bachelor's degrees awarded in Parks, recreation, leisure, fitness, and kinesiology and Total U.S. grain export volume. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Peculiar Parks, Plentiful Protein: Examining the Exquisite Entanglement Between Bachelor's Degrees in Parks, Recreation, Leisure, Fitness, and Kinesiology and Total U.S. Grain Export Volume

[[ABSTRACT]]
This peculiar paper plunges into the perplexing partnership between the output of Bachelor's degrees in the fields of parks, recreation, leisure, fitness, and kinesiology and the total volume of grain exports in the United States. With an eye toward uncovering unforeseen connections, we leveraged data from the National Center for Education Statistics and Statista to explore this rather enigmatic correlation. Our findings unveiled a robust correlation coefficient of 0.7988008, with a statistically significant p-value of less than 0.01 for the years 2012 to 2021.

Our study delves deep into the realms of academia and agriculture, seeking to shed light on this unexpected affiliation. While the conventional academic pursuits in this domain may not seem intertwined with the world of grain exports at first glance, our analysis suggests a peculiar juxtaposition. So join us on this scholarly sojourn as we untangle the enigma of education and agriculture, and unearth the unexpected intersections that abound in our ever-curious world.

[[INTRDUCTION]]
As we venture deeper into the often enigmatic realm of academic analysis, we find ourselves confronted with curious connections that defy conventional wisdom. In this scholarly pursuit, we turn our attention to the peculiar pairing of Bachelor's degrees in parks, recreation, leisure, fitness, and kinesiology, with the unassuming hero of the agricultural world, grain exports.
The field of parks, recreation, and leisure has long been associated with activities that indulge the body and mind, from leisurely strolls in picturesque settings to the high-spirited pursuit of physical fitness. On the other hand, the agricultural domain, particularly the export of grains, has been a stalwart contributor to the provision of sustenance and nourishment across the globe. The juxtaposition of these seemingly disparate spheres evokes a sense of intrigue, akin to stumbling upon a forgotten carnival ride amidst a serene wheat field.
As we embark on this academic odyssey, we seek to unravel the entangled nature of these two realms. While initial skepticism may abound, our endeavor is driven by the resolute belief that hidden beneath the surface lies a connection waiting to be unearthed, not unlike discovering the surprising fusion of flavors in an unusual culinary creation.
In the realm of statistical analysis, our examination reveals a robust correlation coefficient, standing as a testament to the unexpected kinship we aim to elucidate. However, beyond the data lies the allure of discovery, akin to stumbling upon a witty, hidden message in a crossword puzzle.
So, as we delve into the recesses of academia and agriculture, let us open our minds to the possibility that the seemingly incongruous can hold hands in a waltz of correlation and uncover the exquisite entanglement between these seemingly unrelated domains. Join us, dear reader, as we set out to dissect this peculiar puzzle and savor the flavor of scholarly serendipity.

[[RESULTS]]
The statistical analysis of the data gathered from the National Center for Education Statistics and Statista yielded some compelling results. Over the period from 2012 to 2021, our research unearthed a robust correlation coefficient of 0.7988008 between the number of Bachelor's degrees awarded in parks, recreation, leisure, fitness, and kinesiology and the total volume of grain exports in the United States. This finding suggests a fairly strong positive linear relationship between the two variables, reminiscent of finding a well-hidden Easter egg in an expansive, data-filled meadow.
Furthermore, the calculated r-squared value of 0.6380828 indicates that approximately 63.8% of the variability in the grain export volume can be explained by the variation in the number of Bachelor's degrees awarded in the specified fields. This result is not dissimilar to finally connecting the dots in a complicated maze, discovering the unexpected way in which these seemingly unrelated realms intertwine.
The p-value of less than 0.01 for the correlation coefficient provides strong evidence against the null hypothesis, firmly establishing the statistical significance of the relationship. A result this striking is akin to stumbling upon a diamond in the rough, or perhaps a kernel of wheat in a haystack.
Moreover, the scatterplot presented in Fig. 1 portrays a clear, upward-sloping trend, illustrating the conspicuous correlation between the variables. This visualization is akin to witnessing a magic trick that reveals the unexpected connection between two distinct realms, leaving scholars and spectators alike in awe of the unexpected dance of academia and agriculture.
In summary, our findings illuminate a previously overlooked harmony between the confounding domains of higher education and grain exports, highlighting the necessity of exploring uncharted intellectual territories and embracing the delightful surprises that await amidst the labyrinth of data and knowledge.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has delved into the rather unexpected entanglement between the awarding of Bachelor's degrees in parks, recreation, leisure, fitness, and kinesiology and the total volume of grain exports in the United States. The robust correlation coefficient of 0.7988008 serves as a beacon, guiding us through the peculiar yet enchanting labyrinth of statistics and academia, not unlike the feeling of finally finding a missing puzzle piece beneath the sofa cushions.

The r-squared value of 0.6380828 has provided both illumination and intrigue, akin to stumbling upon a treasure map hidden within the pages of a dense academic manuscript. Meanwhile, the p-value of less than 0.01 serves as a resounding applause to the unexpected waltz of scholarly topics, much like discovering a diamond in the rough while sifting through granular data.

Our findings have not only shed light on this captivating correlation but also opened the door to a world of scholarly serendipity, revealing the fruitful rewards of exploring uncharted intellectual territories. It's as if we've uncovered the elusive pot of gold at the end of the rainbow, nestled within the seemingly disparate realms of education and agriculture.

In the grand symphony of scholarly pursuits, our research has offered a newfound perspective on the harmonious interplay between fields that may at first seem incongruous. The scatterplot, much like a piece of abstract art, vividly portrays the unsuspected choreography between these domains, leaving scholars and readers alike in awe of the whimsical dance of data and knowledge.

In light of these compelling findings, it is evident that no further research in this rather peculiar partnership between parks, recreation, leisure, fitness, and kinesiology and U.S. grain export volume is needed. It's time to bid adieu to this curious conundrum and move on to unraveling the next delightful enigma that awaits in the world of academic exploration. After all, there are plenty of peculiar pairings left to investigate in the grand tapestry of scholarly pursuits!

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited Peculiar Parks, Plentiful Protein: Examining the Exquisite Entanglement Between Bachelor's Degrees in Parks, Recreation, Leisure, Fitness, and Kinesiology and Total U.S. Grain Export Volume. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Recreationomics

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Peculiar Parks, Plentiful Protein: Examining the Exquisite Entanglement Between Bachelor's Degrees in Parks, Recreation, Leisure, Fitness, and Kinesiology and Total U.S. Grain Export Volume. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Recreational Physiology and Grain Export Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Peculiar Parks, Plentiful Protein: Examining the Exquisite Entanglement Between Bachelor's Degrees in Parks, Recreation, Leisure, Fitness, and Kinesiology and Total U.S. Grain Export Volume with an abstract of This peculiar paper plunges into the perplexing partnership between the output of Bachelor's degrees in the fields of parks, recreation, leisure, fitness, and kinesiology and the total volume of grain exports in the United States. With an eye toward uncovering unforeseen connections, we leveraged data from the National Center for Education Statistics and Statista to explore this rather enigmatic correlation. Our findings unveiled a robust correlation coefficient of 0.7988008, with a statistically significant p-value of less than 0.01 for the years 2012 to 2021.
Our study delves deep into the realms of academia and agriculture, seeking to shed light on this unexpected affiliation. While the conventional academic pursuits in this domain may not seem intertwined with the world of grain exports at first glance, our analysis suggests a peculiar juxtaposition. So join us on this scholarly sojourn as we untangle the enigma of education and agriculture, and unearth the unexpected intersections that abound in our ever-curious world.

ChatGPT:

bachelor's degrees, parks and recreation, leisure and fitness, kinesiology, grain export, United States, correlation, National Center for Education Statistics, agriculture, academia, academic research

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

Bachelor's degrees awarded in Parks & Recreation
Detailed data title: Bachelor's degrees conferred by postsecondary institutions, in field of study: Parks, recreation, leisure, fitness, and kinesiology
Source: National Center for Education Statistics
See what else correlates with Bachelor's degrees awarded in Parks & Recreation

Total U.S. grain export volume
Source: Statista
See what else correlates with Total U.S. grain export volume

Correlation r = 0.7988008 (Pearson correlation coefficient)
Correlation is a measure of how much the variables move together. If it is 0.99, when one goes up the other goes up. If it is 0.02, the connection is very weak or non-existent. If it is -0.99, then when one goes up the other goes down. If it is 1.00, you probably messed up your correlation function.

r² = 0.6380828 (Coefficient of determination)
This means 63.8% of the change in the one variable (i.e., Total U.S. grain export volume) is predictable based on the change in the other (i.e., Bachelor's degrees awarded in Parks & Recreation) over the 10 years from 2012 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0056.^Show 0.0055793671277333030000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.8 in 0.56% of random cases. Said differently, if you correlated 179 random variables^Note Which I absolutely did.
with the same 9 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 9 because we have two variables measured over a period of 10 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.34, 0.95 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!

All values for the years included above: ^Note If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Bachelor's degrees awarded in Parks & Recreation (Degrees awarded)	38998	42628	46047	49008	50912	53292	53887	53540	53749	54294
Total U.S. grain export volume (Million Metric Tons)	51.5	74.9	80.5	78.7	93.7	92.5	81.2	77.4	104.4	96.4

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."

# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([38998,42628,46047,49008,50912,53292,53887,53540,53749,54294,])
array_2 = np.array([51.5,74.9,80.5,78.7,93.7,92.5,81.2,77.4,104.4,96.4,])
array_1_name = "Bachelor's degrees awarded in Parks & Recreation"
array_2_name = "Total U.S. grain export volume"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)

Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. ^Note Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Bachelor's degrees awarded in Parks & Recreation
Line chart for only Total U.S. grain export volume
AI-generated correlation image
The spurious research paper: Peculiar Parks, Plentiful Protein: Examining the Exquisite Entanglement Between Bachelor's Degrees in Parks, Recreation, Leisure, Fitness, and Kinesiology and Total U.S. Grain Export Volume

View another random correlation

How fun was this correlation?

Your correlation inspection deserves a standing ovation!

Correlation ID: 1488 · Black Variable ID: 1286 · Red Variable ID: 293


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: